菜单
Expose auto_route/local_chat/fusion/find_skills/infra_tips to Hermes-Agent (or any framework that expects OpenAI-function-calling tool specs instead of MCP) — plus a one-call MCP config generator for the zero-code path if the framework already speaks MCP. Use when connecting botte-secrète's routing belt to another agent framework.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Memory as a learnable skill — store, recall, compress, and consolidate agent memories. Inspired by Stanford AutoMem.
Auto-decide whether a task runs on a LOCAL model or a CLOUD model (DeepSeek, GLM, Nemotron, Grok, Gemma, …) from an automatic effort estimate, and run multi-model fusion (cascade, draft→refine, vote). Use when the user wants automatic local-vs-cloud routing, to add cloud LLM providers, to make local and cloud models collaborate, or mentions effort-based routing, model fusion/ensemble, OpenRouter, DeepSeek, GLM, Nemotron, or Grok.
Fenêtres de contexte pour boucles rétroactives — charge seulement les deltas.
Optimisations DAG/RAG — waves, pruning, memoization, routing.
Generate one self-contained, timestamped HTML dashboard of the system's cost picture — routing savings (control loop), metric trends, current metrics, and the cost of outstanding fixes. Also renders as a live ANSI terminal view (--tui, --watch) and serves a live HTTP API (api.py). Use when the user wants a single visual view of cost/savings/health over time, or a live terminal view they don't have to open a browser for.
Append-only JSONL decision log (.botte/events.jsonl) that every filter in the belt writes to — routing, cache hits, escalations, micro-NN outputs. The single source of truth demo mode, the live dashboard, and session replay all read from. Use when you want to see or emit a live feed of routing/cache/escalation decisions, or when building a tool that needs to watch the belt work in real time.
| name | hermes_bridge |
| layer | EXPOSE |
| description | Expose auto_route/local_chat/fusion/find_skills/infra_tips to Hermes-Agent (or any framework that expects OpenAI-function-calling tool specs instead of MCP) — plus a one-call MCP config generator for the zero-code path if the framework already speaks MCP. Use when connecting botte-secrète's routing belt to another agent framework. |
botte-secrète already runs a standard MCP server (skills.llm_mcp.server,
stdio JSON-RPC). If the target framework speaks MCP, that's the whole
integration — no code in this module runs:
python -m skills.hermes_bridge.cli config --cwd /path/to/botte-secrete
# → paste the printed {"mcpServers": {...}} block into the framework's MCP config
This module exists for frameworks — [[hermes-second-brain]] among them — that instead expect a flat list of OpenAI-function-calling tool specs + a dispatcher, a common shape for agents built before/without MCP support.
python -m skills.hermes_bridge.cli schemas # the 5 tool specs, OpenAI-shaped
python -m skills.hermes_bridge.cli call botte_auto_route --prompt "rename x to y"
from skills.hermes_bridge import TOOL_SCHEMAS, dispatch
# register TOOL_SCHEMAS with the framework's tool-calling mechanism, then:
dispatch("botte_auto_route", {"prompt": "..."}) # → JSON string, same shape as the MCP tool
Deliberately a subset of the ~35-tool MCP surface — the ones that matter for a second-brain / routing integration:
| tool | what it does |
|---|---|
botte_auto_route | decide local-vs-cloud (0 tokens); execute=true to actually run it |
botte_local_chat | run a prompt on a local model — 0 cloud tokens |
botte_fusion | cascade / draft_refine / vote — models collaborating |
botte_find_skills | 0-token local search over installed skill catalogs |
botte_infra_tips | hardware/software setup advice for running local models |
Every task [[hermes-second-brain]] would otherwise send straight to its own
model gets a chance to resolve locally or via the cheapest capable tier
first — see [[bench]] for the measured (not asserted) savings from that.
botte_find_skills also gives Hermes 0-token access to the local skill
catalog instead of re-deriving capabilities from scratch each session.
Related: [[llm_mcp]] (the native MCP server this bridges from), [[auto_router]],
[[bench]] (the proof), docs/integrations/hermes.md (the full integration write-up).